{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FITRE2H2ORL3APQ6F3Y5MGTJBU","short_pith_number":"pith:FITRE2H2","schema_version":"1.0","canonical_sha256":"2a271268fa7457b03e1e2ef1d61a690d18593f64befc49eecf5135d995d94f3d","source":{"kind":"arxiv","id":"2008.12914","version":1},"attestation_state":"computed","paper":{"title":"Data augmentation using prosody and false starts to recognize non-native children's speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Hemant Kathania, Mikko Kurimo, Mittul Singh, Tam\\'as Gr\\'osz","submitted_at":"2020-08-29T05:32:32Z","abstract_excerpt":"This paper describes AaltoASR's speech recognition system for the INTERSPEECH 2020 shared task on Automatic Speech Recognition (ASR) for non-native children's speech. The task is to recognize non-native speech from children of various age groups given a limited amount of speech. Moreover, the speech being spontaneous has false starts transcribed as partial words, which in the test transcriptions leads to unseen partial words. To cope with these two challenges, we investigate a data augmentation-based approach. Firstly, we apply the prosody-based data augmentation to supplement the audio data. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.12914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-29T05:32:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"71bddec4b678f3e73b8fda3fbde1e7be30afa4fc49087ca3e643b00088342f3e","abstract_canon_sha256":"f63c4a4554d8c4cd6ffad943ec31bec9cad92ea4b96ad5e89a4bedeff558b0ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:31:32.447931Z","signature_b64":"j+3/Zh8/ld18DGE/m8ksV9XWwU6z3FSoP7L3jPMcqUy30lCmqUsQ45huXyirDDDTiy8DVO64CJt9QkGbAuvzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a271268fa7457b03e1e2ef1d61a690d18593f64befc49eecf5135d995d94f3d","last_reissued_at":"2026-07-05T01:31:32.447581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:31:32.447581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data augmentation using prosody and false starts to recognize non-native children's speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Hemant Kathania, Mikko Kurimo, Mittul Singh, Tam\\'as Gr\\'osz","submitted_at":"2020-08-29T05:32:32Z","abstract_excerpt":"This paper describes AaltoASR's speech recognition system for the INTERSPEECH 2020 shared task on Automatic Speech Recognition (ASR) for non-native children's speech. The task is to recognize non-native speech from children of various age groups given a limited amount of speech. Moreover, the speech being spontaneous has false starts transcribed as partial words, which in the test transcriptions leads to unseen partial words. To cope with these two challenges, we investigate a data augmentation-based approach. Firstly, we apply the prosody-based data augmentation to supplement the audio data. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.12914","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.12914/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.12914","created_at":"2026-07-05T01:31:32.447639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.12914v1","created_at":"2026-07-05T01:31:32.447639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.12914","created_at":"2026-07-05T01:31:32.447639+00:00"},{"alias_kind":"pith_short_12","alias_value":"FITRE2H2ORL3","created_at":"2026-07-05T01:31:32.447639+00:00"},{"alias_kind":"pith_short_16","alias_value":"FITRE2H2ORL3APQ6","created_at":"2026-07-05T01:31:32.447639+00:00"},{"alias_kind":"pith_short_8","alias_value":"FITRE2H2","created_at":"2026-07-05T01:31:32.447639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04814","citing_title":"Pitch Accent Detection improves Pretrained Automatic Speech Recognition","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU","json":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU.json","graph_json":"https://pith.science/api/pith-number/FITRE2H2ORL3APQ6F3Y5MGTJBU/graph.json","events_json":"https://pith.science/api/pith-number/FITRE2H2ORL3APQ6F3Y5MGTJBU/events.json","paper":"https://pith.science/paper/FITRE2H2"},"agent_actions":{"view_html":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU","download_json":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU.json","view_paper":"https://pith.science/paper/FITRE2H2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.12914&json=true","fetch_graph":"https://pith.science/api/pith-number/FITRE2H2ORL3APQ6F3Y5MGTJBU/graph.json","fetch_events":"https://pith.science/api/pith-number/FITRE2H2ORL3APQ6F3Y5MGTJBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU/action/storage_attestation","attest_author":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU/action/author_attestation","sign_citation":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU/action/citation_signature","submit_replication":"https://pith.science/pith/FITRE2H2ORL3APQ6F3Y5MGTJBU/action/replication_record"}},"created_at":"2026-07-05T01:31:32.447639+00:00","updated_at":"2026-07-05T01:31:32.447639+00:00"}